© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84489
    Prev
    Next
    INDEX
    Explanations

    URLs and web link structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ork
    -0.06
    zap
    -0.06
    char
    -0.06
    ogg
    -0.06
    į
    -0.05
     poste
    -0.05
    uckle
    -0.05
    fonts
    -0.05
    apper
    -0.05
    esk
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
     journal
    0.08
     diss
    0.07
     abstract
    0.07
    .ncbi
    0.07
    abstract
    0.07
    -article
    0.07
     journals
    0.07
    /article
    0.07
    iler
    0.07
    Activations Density 0.018%

    No Known Activations